C#将html代码转换成文本代码

 /// <summary>
     /// 去除HTML标记
     /// </summary>
     /// <param name="strHtml">包括HTML的源码 </param>
     /// <returns>已经去除后的文字</returns>
     public static string StripHTML(string strHtml)
     {
         string[] aryReg = { @"<script[^>]*?>.*?</script>", @"<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(\\[""'tbnr]|[^\7])*?\7|\w+)|.{0})|\s)*?(\/\s*)?>", @"([\r\n])[\s]+", @"&(quot|#34);", @"&(amp|#38);", @"&(lt|#60);", @"&(gt|#62);", @"&(nbsp|#160);", @"&(iexcl|#161);", @"&(cent|#162);", @"&(pound|#163);", @"&(copy|#169);", @"&#(\d+);", @"-->", @"<!--.*\n" };
         string[] aryRep = { "", "", "", "\"", "&", "<", ">", " ", "\xa1", "\xa2", "\xa3", "\xa9", "", "\r\n", "" };
         string newReg = aryReg[];
         string strOutput = strHtml;
         for (int i = ; i < aryReg.Length; i++)
         {
             Regex regex = new Regex(aryReg[i], RegexOptions.IgnoreCase);
             strOutput = regex.Replace(strOutput, aryRep[i]);
         }
         strOutput.Replace("<", ""); strOutput.Replace(">", "");
         strOutput.Replace("\r\n", ""); return strOutput;
     }